Information processing apparatus, information processing method, and storage medium

Abstract

Provided is an information processing apparatus including: a character recognition unit configured to perform a character recognition process on an image of a processing target document; a generation unit configured to generate an instruction message based on a result of the character recognition process, the instruction message being a message for causing a large language model to reply a document type of the processing target document; a transmission unit configured to transmit the instruction message in order to obtain a reply to the instruction message from the large language model; and a reception unit configured to receive the reply to the instruction message from the large language model.

What is claimed is: 
     
         1 . An information processing apparatus comprising:
 a character recognition unit configured to perform a character recognition process on an image of a processing target document;   a generation unit configured to generate an instruction message based on a result of the character recognition process, the instruction message being a message for causing a large language model to reply a document type of the processing target document;   a transmission unit configured to transmit the instruction message in order to obtain a reply to the instruction message from the large language model; and   a reception unit configured to receive the reply to the instruction message from the large language model.   
     
     
         2 . The information processing apparatus according to  claim 1 , wherein
 the generated instruction message is a message for causing the large language model to reply the document type of the document based on character strings obtained by the character recognition process.   
     
     
         3 . The information processing apparatus according to  claim 1 , further comprising
 an extraction unit configured to extract at least a character string corresponding to a predetermined item from among character strings obtained by the character recognition process, wherein   the generation unit generates the instruction message for causing the large language model to reply the document type of the processing target document based on the character string corresponding to the predetermined item.   
     
     
         4 . The information processing apparatus according to  claim 3 , wherein the predetermined item is a title. 
     
     
         5 . The information processing apparatus according to  claim 3 , wherein
 the predetermined item includes a plurality of items.   
     
     
         6 . The information processing apparatus according to  claim 3 , wherein
 the extraction unit extracts a character string corresponding to the predetermined item by inputting the character strings obtained by the character recognition process into a trained model, and   the generation unit generates the instruction message for causing the large language model to reply the document type of the processing target document based on the character string corresponding to the predetermined item.   
     
     
         7 . The information processing apparatus according to  claim 1 , wherein
 the instruction message includes a first question for causing the large language model to answer whether the document type of the processing target document is one of a plurality of document types set in advance.   
     
     
         8 . The information processing apparatus according to  claim 7 , wherein
 the instruction message includes a second question for causing the large language model to reply a document type other than the plurality of document types as the document type of the processing target document in a case where the document type of the processing target document is none of the plurality of document types.   
     
     
         9 . The information processing apparatus according to  claim 8 , wherein
 the instruction message includes a third question for causing the large language model to reply a reason for the replies to the first question and the second question.   
     
     
         10 . The information processing apparatus according to  claim 8 , further comprising
 a determination unit configured to input a group of character strings obtained by the character recognition process into a trained model to determine the document type of the processing target document, wherein   the trained model is a trained model trained to output information indicating one of the plurality of document types.   
     
     
         11 . The information processing apparatus according to  claim 10 , further comprising
 a display control unit configured to display at least one of the document type determined by the determination unit or the document type received from the large language model on a display unit as the document type of the processing target document.   
     
     
         12 . The information processing apparatus according to  claim 11 , wherein
 in a case where a user designates correction of the displayed document type, the display control unit accepts the correction.   
     
     
         13 . The information processing apparatus according to  claim 12 , wherein
 the display control unit displays the document type determined by the determination unit on the display unit as the document type of the processing target document, and in a case where the large language model outputs a first document type being a document type other than the plurality of document types as the reply to the second question, displays the first document type on the display unit as a candidate for a corrected character string.   
     
     
         14 . The information processing apparatus according to  claim 8 , further comprising
 a setting unit configured to set document types to be included as the plurality of document types.   
     
     
         15 . The information processing apparatus according to  claim 14 , wherein
 in a case where the large language model outputs a first document type being a document type other than the plurality of document types as the reply to the second question and a user selects the first document type as the document type of the processing target document, the setting unit sets the first document type as a document type included in the plurality of document types.   
     
     
         16 . The information processing apparatus according to  claim 1 , further comprising
 a setting unit configured to set one or more large language models to be caused to reply to the instruction message, wherein   the transmission unit transmits the instruction message to the set one or more large language models.   
     
     
         17 . An information processing method comprising:
 performing a character recognition process on an image of a processing target document;   generating an instruction message based on a result of the character recognition process, the instruction message being a message for causing a large language model to reply a document type of the processing target document;   transmitting the instruction message in order to obtain a reply to the instruction message from the large language model; and   receiving the reply to the instruction message from the large language model.   
     
     
         18 . A non-transitory computer readable storage medium storing a program which causes a computer to:
 perform a character recognition process on an image of a processing target document;   generate an instruction message based on a result of the character recognition process, the instruction message being a message for causing a large language model to reply a document type of the processing target document;   transmit the instruction message in order to obtain a reply to the instruction message from the large language model; and   receive the reply to the instruction message from the large language model.